Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The use of deep learning and 2-D wavelet scalograms for power quality disturbances classification
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Energy Science.ORCID iD: 0000-0002-3625-8578
Federal University of Itajuba, Av. BPS 1303, 37500 903 Itajuba, Brazil.ORCID iD: 0000-0003-1080-462x
2023 (English)In: Electric power systems research, ISSN 0378-7796, E-ISSN 1873-2046, Vol. 214, no Part A, article id 108834Article in journal (Refereed) Published
Abstract [en]

This work investigates the use of advanced signal processing and deep Learning for pattern recognition and classification of signals with power quality disturbances. For this purpose, the continuous wavelet transform is used to generate 2-D images with the time–frequency representation from signals with voltage disturbances. The work aims to use convolutional neural networks to classify this data according to the images’ distortion. In this implementation of artificial intelligence, specific stages of design, training, validation, and testing were carried out for a model elaborated from the scratch and a transfer learning technique with the pre-trained networks SqueezeNet, GoogleNet, and ResNet-50. The work was developed in the MATLAB/Simulink software, all signal processing stages, CNN design, simulation, and the investigated data generation. All steps have their objectives fulfilled, culminating in the excellent execution and development of the research. The results sought high precision for the model from scratch and ResNet-50 in classify the test set. The other two models obtained not-so-high accuracy, and the results are consistent when compared with different methodologies. The main contributions of the paper are: (i) developing a methodology to use DL and transfer learning on the classification of voltage disturbances; (ii) using a 2-D representation that incorporates time and frequency information that characterizes several PQ issues; (iii) conducting a study case that shows the suitability of CNN as a tool for voltage disturbance classification, with specific application for 2-D images. Considerations about the results were pointed out.

Place, publisher, year, edition, pages
Elsevier, 2023. Vol. 214, no Part A, article id 108834
Keywords [en]
Power quality, Advanced signal processing, Deep Learning, Convolutional neural networks, Smart grids
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electric Power Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-93656DOI: 10.1016/j.epsr.2022.108834ISI: 001027895100001Scopus ID: 2-s2.0-85139597612OAI: oai:DiVA.org:ltu-93656DiVA, id: diva2:1704972
Note

Validerad;2022;Nivå 2;2022-10-20 (hanlid);

Funder: CAPES; CNPq; FAPEMIG; INERGE

Available from: 2022-10-20 Created: 2022-10-20 Last updated: 2024-03-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Salles, Rafael S.

Search in DiVA

By author/editor
Salles, Rafael S.Ribeiro, Paulo F.
By organisation
Energy Science
In the same journal
Electric power systems research
Other Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 153 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf